Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to capturing and handling output from processes in Python scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    log output messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.79
     ब्रेकडाउन
    -0.68
     disambiguazione
    -0.68
     typelib
    -0.60
     transférez
    -0.57
     Infórmanos
    -0.56
    elemField
    -0.55
    ftagPool
    -0.55
     transfieras
    -0.54
     BoxDecoration
    -0.51
    POSITIVE LOGITS
     contenido
    0.41
     linguagem
    0.40
     messages
    0.40
    kregen
    0.39
     mensajes
    0.38
    conomie
    0.38
     conteúdo
    0.37
     comunicaciones
    0.36
     contents
    0.35
     mensagens
    0.35
    Act Density 0.025%

    No Known Activations